This repository has been archived by the owner on Jan 15, 2024. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 538
Word embeddings update #159
Merged
Merged
Changes from 1 commit
Commits
Show all changes
38 commits
Select commit
Hold shift + click to select a range
3ab1d2c
Mask accidental hits
leezu b69382e
Simplify frequent token subsampling
leezu a74ac4a
Remove tqdm dependency
leezu 28528fa
Simplifications
leezu 68185ac
Support read from vec format
leezu c9dc46a
Add back DeduplicatedFasttext
leezu d85af54
Average the subword embeddings for FastText
leezu 73bde08
Fix Fasttext hash function for ngrams containing non-ASCII data
leezu 517a37e
Merge train_word2vec and train_fasttext
leezu 880acb9
Clean up fasttext evaluation binary script
leezu d4a3874
Remove waitall
leezu 32a1839
Only evaluate at end of training by default
leezu 68ad3f5
Set mxnet env variables
leezu 0007f67
Increase number of subword units considered by default
leezu 9fe1ca6
Update hyperparameters
leezu 9700e11
Fix cbow
leezu 61f9f5f
Use separate batch-size for evaluation
leezu b338e8d
Fix lint
leezu 09fb6df
Rerun extended_results.ipynb and commit dependant results/*tvs files …
leezu e215118
Clean up TokenEmbedding API docs
leezu ab1b5ed
Refactor TokenEmbedding OOV inference
leezu 4d02b7a
Use GluonNLP load_fasttext_model for word embeddings evaluation script
leezu f3b257b
Add tests
leezu 6eb685f
Remove deprecated to_token_embedding method from train/embedding.py
leezu 35bcb7b
Merge TokenEmbedding.extend in TokenEmbedding.__setitem__
leezu 7da4c6f
Use full link to #11314
leezu 08858d7
Improve test coverage
leezu 5e960fa
Update notebook
leezu 348c46f
Fix doc
leezu f5cfc84
Cache word ngram hashes
leezu 7e531d4
Move results to dmlc/web-data
leezu 897b000
Move candidate_sampler to scripts
leezu 1637ef7
Update --negative doc
leezu 546a9af
Match old default behavior of TokenEmbedding and add warnings
leezu 4a32070
Match weight context in UnigramCandidateSampler
leezu c307061
Add Pad test case with empty ndarray input
leezu e90bd33
Address review comments
leezu 9c79163
Fix doc and superfluous inheritance
leezu File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Fix cbow
- Loading branch information
commit 9700e1195289432f74d687f20f69c38f93711548
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I understand we want to minimize the dot(l(s(w_t,w_c)) + l(-s(w_t,w_c))), but what do we need word_context_mask mean here?